Hippocratic AI
Forward Deployed Engineer
About this role
Hippocratic AI seeks a Forward Deployed Engineer to own AI system deployments in healthcare, combining advanced LLM expertise with production engineering. You'll design and implement RAG pipelines, tool-calling architectures, and reliable integrations while working directly with customers to deploy mission-critical conversational AI systems.
What you'll do
- Design and implement RAG pipelines and LLM techniques (tool-calling, LLM-as-judge) tailored to healthcare customer challenges
- Build production Python code using LangChain, LangSmith, and modern AI frameworks with strong error handling
- Architect integrations connecting to customer systems (EHRs, data warehouses) via APIs, tool-calling, and Model Context Protocol
- Execute end-to-end deployments including infrastructure setup, testing, monitoring, and go-live coordination
- Monitor production systems, respond to incidents, troubleshoot with customers, and drive operational improvements
- Collaborate with Deployment Strategists and customers to identify problems early and build technical confidence
What they're looking for
- Python software development (3-5 years production experience)
- LLM frameworks (LangChain, LangSmith)
- RAG pipeline design and implementation
- LLM techniques (prompt engineering, tool-calling, LLM-as-judge)
- API and database integration with async patterns
- Production monitoring and incident response
- Model Context Protocol (MCP) or similar tool integration
- Healthcare IT systems (FHIR, HL7, EHR integrations)
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Hippocratic AI
Hippocratic AI builds safety-focused generative AI systems for healthcare, developing LLM-powered clinical dialogue platforms and integrations with electronic health records. The company is hiring infrastructure engineers, performance specialists, prompt engineers, and integration engineers to optimize AI inference, ensure system reliability, and connect healthcare data ecosystems.
View all jobs at Hippocratic AILikely interview questions
- Walk us through a production RAG implementation you've built—how did you handle retrieval accuracy and relevance in a real system?
- Describe your experience with tool-calling or function-calling patterns in LLM applications. What challenges did you encounter?